Interactive Networks

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✓ tibble  3.1.6     ✓ purrr   0.3.4
✓ tidyr   1.1.4     ✓ forcats 0.5.1
✓ readr   2.0.2     
── Conflicts ───────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x tidyr::extract()   masks magrittr::extract()
x dplyr::filter()    masks stats::filter()
x dplyr::lag()       masks stats::lag()
x purrr::set_names() masks magrittr::set_names()

Attaching package: ‘jsonlite’

The following object is masked from ‘package:purrr’:

    flatten

Loading required package: NLP

Attaching package: ‘NLP’

The following object is masked from ‘package:ggplot2’:

    annotate

Package version: 3.2.0
Unicode version: 13.0
ICU version: 69.1
Parallel computing: 8 of 8 threads used.
See https://quanteda.io for tutorials and examples.

Attaching package: ‘quanteda’

The following object is masked from ‘package:tm’:

    stopwords

The following objects are masked from ‘package:NLP’:

    meta, meta<-


Attaching package: ‘rvest’

The following object is masked from ‘package:readr’:

    guess_encoding

Loading required package: RColorBrewer

‘network’ 1.17.1 (2021-06-12), part of the Statnet Project
* ‘news(package="network")’ for changes since last version
* ‘citation("network")’ for citation information
* ‘https://statnet.org’ for help, support, and other information


Attaching package: ‘igraph’

The following objects are masked from ‘package:network’:

    %c%, %s%, add.edges, add.vertices, delete.edges, delete.vertices, get.edge.attribute, get.edges,
    get.vertex.attribute, is.bipartite, is.directed, list.edge.attributes, list.vertex.attributes,
    set.edge.attribute, set.vertex.attribute

The following object is masked from ‘package:formattable’:

    normalize

The following objects are masked from ‘package:purrr’:

    compose, simplify

The following object is masked from ‘package:tidyr’:

    crossing

The following object is masked from ‘package:tibble’:

    as_data_frame

The following objects are masked from ‘package:dplyr’:

    as_data_frame, groups, union

The following objects are masked from ‘package:stats’:

    decompose, spectrum

The following object is masked from ‘package:base’:

    union

Network visualization using output from text model

Data preparation

edgelist <- read.csv("../../../Data/Text_Model_Data/edgelist.csv")
edgelist

Indicator title

indicator_info <- read.csv("../../../Data/Text_Model_Data/indicator_att.csv")
library(stringr)
str_replace_all(indicator_info$Indicator, fixed(" "), "")
Textdata <- datatable(indicator_info, rownames=TRUE, caption=htmltools::tags$caption(style="caption-side: bottom; text-align: center;", "Innovative counties in the U.S."), filter="top", extensions="Buttons", options=list(dom = "Bfrtip", buttons = c("colvis", "copy", "csv", "excel", "pdf", "print")))
Textdata

For future classification of indicators into the goals they belong to, create the nodes dataframe:

nodes <- edgelist %>%
  select(indicator, related_indicator)
nodes <- data.frame(Indicator = unlist(nodes, use.names = FALSE))
nodes <- distinct(nodes)
str_replace_all(nodes$Indicator, fixed(" "), "")

  [1] "1.1.1"   "1.2.2"   "1.3.1"   "1.4.1"   "1.4.2"   "1.5.1"   "1.5.2"   "1.5.3"   "1.5.4"   "1.a.1"   "1.a.2"   "2.2.1"  
 [13] "2.2.2"   "2.2.3"   "2.3.1"   "2.3.2"   "2.4.1"   "2.5.1"   "2.5.2"   "2.a.1"   "2.a.2"   "2.b.1"   "2.c.1"   "3.1.1"  
 [25] "3.2.1"   "3.3.1"   "3.3.2"   "3.4.1"   "3.4.2"   "3.6.1"   "3.7.2"   "3.8.2"   "3.9.2"   "3.b.2"   "4.1.1"   "4.1.2"  
 [37] "4.2.1"   "4.2.2"   "4.3.1"   "4.6.1"   "4.7.1"   "4.a.1"   "4.b.1"   "4.c.1"   "5.2.1"   "5.2.2"   "5.3.1"   "5.4.1"  
 [49] "5.6.1"   "5.6.2"   "5.a.1"   "5.a.2"   "5.b.1"   "6.1.1"   "6.3.2"   "6.4.1"   "6.4.2"   "6.5.2"   "6.6.1"   "6.a.1"  
 [61] "6.b.1"   "7.1.1"   "7.2.1"   "7.3.1"   "7.a.1"   "7.b.1"   "8.1.1"   "8.2.1"   "8.3.1"   "8.4.1"   "8.4.2"   "8.5.1"  
 [73] "8.6.1"   "8.7.1"   "8.8.2"   "8.9.1"   "8.a.1"   "8.b.1"   "9.2.1"   "9.2.2"   "9.3.1"   "9.3.2"   "9.4.1"   "9.5.1"  
 [85] "9.5.2"   "9.a.1"   "9.b.1"   "10.1.1"  "10.3.1"  "10.6.1"  "10.7.1"  "10.7.4"  "10.a.1"  "10.b.1"  "11.1.1"  "11.3.1" 
 [97] "11.3.2"  "11.5.1"  "11.5.2"  "11.6.1"  "11.7.2"  "11.a.1"  "11.b.1"  "11.b.2"  "12.1.1"  "12.2.1"  "12.4.1"  "12.8.1" 
[109] "13.1.2"  "13.2.1"  "13.2.2"  "14.4.1"  "14.5.1"  "14.6.1"  "14.7.1"  "14.c.1"  "15.1.1"  "15.1.2"  "15.4.1"  "15.7.1" 
[121] "15.9.1"  "15.a.1"  "16.1.1"  "16.1.3"  "16.2.1"  "16.5.2"  "16.6.1"  "16.6.2"  "16.8.1"  "16.10.1" "16.10.2" "16.a.1" 
[133] "17.1.1"  "17.2.1"  "17.4.1"  "17.5.1"  "17.10.1" "17.11.1" "17.15.1" "17.18.2" "17.18.3" "1.2.1"   "1.b.1"   "6.2.1"  
[145] "11.2.1"  "9.1.1"   "3.8.1"   "15.3.1"  "16.b.1"  "14.b.1"  "13.1.1"  "12.3.1"  "13.1.3"  "17.12.1" "17.9.1"  "17.1.2" 
[157] "11.4.1"  "13.3.1"  "12.c.1"  "16.2.3"  "15.6.1"  "3.2.2"   "3.3.3"   "3.9.1"   "3.9.3"   "8.8.1"   "5.3.2"   "16.9.1" 
[169] "5.5.2"   "5.c.1"   "9.c.1"   "17.8.1"  "12.a.1"  "10.2.1"  "17.3.2"  "8.5.2"   "12.2.2"  "12.b.1"  "10.4.1"  "10.c.1" 
[181] "16.1.2"  "16.4.1"  "17.19.2" "12.4.2"  "17.14.1" "13.b.1"  "13.a.1"  "15.b.1"  "17.16.1" "15.2.1"  "15.4.2"  "15.c.1" 
[193] "16.3.1"  "16.3.3"  "16.7.2"  "17.19.1"

#nodes$goal <- stri_match_first_regex(nodes$indicator, "(.*?)\\.")[,2]
#nodes$goal <-as.numeric(nodes$goal)
nodes<-merge(x=nodes,y=indicator_info,by="Indicator",all.x=TRUE)
g<-graph_from_data_frame(edgelist, directed=FALSE, vertices=nodes)
in_degree<-degree(g, mode="in")
in_degree<-as.data.frame(in_degree)
in_degree <- cbind(rownames(in_degree), in_degree)
rownames(in_degree) <- NULL
colnames(in_degree) <- c("Indicator","in_degree")
str_replace_all(in_degree$Indicator, fixed(" "), "")

  [1] "1.1.1"   "1.2.1"   "1.2.2"   "1.3.1"   "1.4.1"   "1.4.2"   "1.5.1"   "1.5.2"   "1.5.3"   "1.5.4"   "1.a.1"   "1.a.2"  
 [13] "1.b.1"   "10.1.1"  "10.2.1"  "10.3.1"  "10.4.1"  "10.6.1"  "10.7.1"  "10.7.4"  "10.a.1"  "10.b.1"  "10.c.1"  "11.1.1" 
 [25] "11.2.1"  "11.3.1"  "11.3.2"  "11.4.1"  "11.5.1"  "11.5.2"  "11.6.1"  "11.7.2"  "11.a.1"  "11.b.1"  "11.b.2"  "12.1.1" 
 [37] "12.2.1"  "12.2.2"  "12.3.1"  "12.4.1"  "12.4.2"  "12.8.1"  "12.a.1"  "12.b.1"  "12.c.1"  "13.1.1"  "13.1.2"  "13.1.3" 
 [49] "13.2.1"  "13.2.2"  "13.3.1"  "13.a.1"  "13.b.1"  "14.4.1"  "14.5.1"  "14.6.1"  "14.7.1"  "14.b.1"  "14.c.1"  "15.1.1" 
 [61] "15.1.2"  "15.2.1"  "15.3.1"  "15.4.1"  "15.4.2"  "15.6.1"  "15.7.1"  "15.9.1"  "15.a.1"  "15.b.1"  "15.c.1"  "16.1.1" 
 [73] "16.1.2"  "16.1.3"  "16.10.1" "16.10.2" "16.2.1"  "16.2.3"  "16.3.1"  "16.3.3"  "16.4.1"  "16.5.2"  "16.6.1"  "16.6.2" 
 [85] "16.7.2"  "16.8.1"  "16.9.1"  "16.a.1"  "16.b.1"  "17.1.1"  "17.1.2"  "17.10.1" "17.11.1" "17.12.1" "17.14.1" "17.15.1"
 [97] "17.16.1" "17.18.2" "17.18.3" "17.19.1" "17.19.2" "17.2.1"  "17.3.2"  "17.4.1"  "17.5.1"  "17.8.1"  "17.9.1"  "2.2.1"  
[109] "2.2.2"   "2.2.3"   "2.3.1"   "2.3.2"   "2.4.1"   "2.5.1"   "2.5.2"   "2.a.1"   "2.a.2"   "2.b.1"   "2.c.1"   "3.1.1"  
[121] "3.2.1"   "3.2.2"   "3.3.1"   "3.3.2"   "3.3.3"   "3.4.1"   "3.4.2"   "3.6.1"   "3.7.2"   "3.8.1"   "3.8.2"   "3.9.1"  
[133] "3.9.2"   "3.9.3"   "3.b.2"   "4.1.1"   "4.1.2"   "4.2.1"   "4.2.2"   "4.3.1"   "4.6.1"   "4.7.1"   "4.a.1"   "4.b.1"  
[145] "4.c.1"   "5.2.1"   "5.2.2"   "5.3.1"   "5.3.2"   "5.4.1"   "5.5.2"   "5.6.1"   "5.6.2"   "5.a.1"   "5.a.2"   "5.b.1"  
[157] "5.c.1"   "6.1.1"   "6.2.1"   "6.3.2"   "6.4.1"   "6.4.2"   "6.5.2"   "6.6.1"   "6.a.1"   "6.b.1"   "7.1.1"   "7.2.1"  
[169] "7.3.1"   "7.a.1"   "7.b.1"   "8.1.1"   "8.2.1"   "8.3.1"   "8.4.1"   "8.4.2"   "8.5.1"   "8.5.2"   "8.6.1"   "8.7.1"  
[181] "8.8.1"   "8.8.2"   "8.9.1"   "8.a.1"   "8.b.1"   "9.1.1"   "9.2.1"   "9.2.2"   "9.3.1"   "9.3.2"   "9.4.1"   "9.5.1"  
[193] "9.5.2"   "9.a.1"   "9.b.1"   "9.c.1"  

nodes<-merge(x=nodes,y=in_degree,by="Indicator",all.x=TRUE)
nodes<-nodes %>%
  select(Indicator, Goal, Indicator_title, in_degree)
nodes

Visualization

In the network graph below, the size of each vertices (each indicator) represents the number of related indicators that are connected to it. The width of the edges linking each indicator is determined according to the similarity score between each pair of related indicators. The indicators are grouped according to the goals they belong to, which are denoted by different colors of the vertices.

edges <- edgelist %>% dplyr::rename(Indicator = indicator)

nodes <- data.frame(id = nodes$Indicator,
                    label = nodes$Indicator,
                    group = nodes$Goal,
                    color = ifelse(nodes$Goal == 1,"#ea1d2d",ifelse(nodes$Goal == 2,"#d19f2a",ifelse(nodes$Goal == 3,"#2d9a47",
                            ifelse(nodes$Goal == 4,"#c22033",ifelse(nodes$Goal == 5,"#ef412a",ifelse(nodes$Goal == 6,"#00add8",
                            ifelse(nodes$Goal == 7,"#fdb714",ifelse(nodes$Goal == 8,"#8f1838",ifelse(nodes$Goal == 9,"#f36e24",
                            ifelse(nodes$Goal == 10,"#e01a83",ifelse(nodes$Goal == 11,"#f99d25",ifelse(nodes$Goal == 12,"#cd8b2a",
                            ifelse(nodes$Goal == 13,"#48773c",ifelse(nodes$Goal == 14,"#007dbb",ifelse(nodes$Goal == 15,"#40ae49",
                            ifelse(nodes$Goal == 16,"#00558a","#1a3668")))))))))))))))),
                    highlight = ifelse(nodes$Goal == 1,"#ea1d2d",ifelse(nodes$Goal == 2,"#d19f2a",ifelse(nodes$Goal == 3,"#2d9a47",
                            ifelse(nodes$Goal == 4,"#c22033",ifelse(nodes$Goal == 5,"#ef412a",ifelse(nodes$Goal == 6,"#00add8",
                            ifelse(nodes$Goal == 7,"#fdb714",ifelse(nodes$Goal == 8,"#8f1838",ifelse(nodes$Goal == 9,"#f36e24",
                            ifelse(nodes$Goal == 10,"#e01a83",ifelse(nodes$Goal == 11,"#f99d25",ifelse(nodes$Goal == 12,"#cd8b2a",
                            ifelse(nodes$Goal == 13,"#48773c",ifelse(nodes$Goal == 14,"#007dbb",ifelse(nodes$Goal == 15,"#40ae49",
                            ifelse(nodes$Goal == 16,"#00558a","#1a3668")))))))))))))))),
                    size = nodes$in_degree*10)

edges <- data.frame(from = edges$Indicator, to=edges$related_indicator, width = edges$similarity_score*4, color='gray')

nodes$shape  <- "dot"  
nodes$shadow <- FALSE

# this section doesn't allow our graph to show up - no idea why. 
# nodes$color.background <- nodes$color 
# nodes$color.border <- nodes$color 
# nodes$color.highlight.background <- nodes$color 
# nodes$color.highlight.border <- nodes$color 


edges$color <- "gray"    # line color  
edges$smooth <- FALSE    # should the edges be curved?
edges$shadow <- FALSE

visnet<-visNetwork(nodes,edges, height = "700px", width = "100%", main="Text Network Model",submain= "UN SDG Indicator Metadata", footer="Zoom in to see indicator name, click/hover to see indicator title") %>%
    visEdges(smooth = FALSE) %>%

  visOptions(selectedBy = "Goal", 
             highlightNearest = TRUE, 
             nodesIdSelection = TRUE) #%>%
  #visLegend(main="Legend",position="right", ncol=1)
visnet
visSave(visnet, file = "Text Network Model.html")

Network visualization using output from the social network model

Indonesia

###Data preparation

edgelistindo <- read.csv("~/Documents/GitHub/G5055_Practicum_Project2/Data/PCA_results/indo_coefficients_sig.csv")
#Some preprocessing
edgelistindo<-edgelistindo%>%
  select(Var1, Var2, value)%>%
  filter(Var1!=Var2)
names(edgelistindo)<-c("from","to","value")
edgelistindo

For future classification of indicators into the goals they belong to, create the nodes dataframe:

indonodes <- edgelistindo %>%
  select(from, to)
indonodes <- data.frame(Indicator = unlist(indonodes, use.names = FALSE))
indonodes <- distinct(indonodes)
#indonodes$goal <- stri_match_first_regex(indonodes$indicator, "(.*?)\\.")[,2]
#indonodes$goal <-as.numeric(indonodes$goal)
indonodes<-merge(x=indonodes,y=indicator_info,by="Indicator",all.x=TRUE)
g2<-graph_from_data_frame(edgelistindo, directed=FALSE, vertices=indonodes)
in_degree<-degree(g2, mode="in")
in_degree<-as.data.frame(in_degree)
in_degree <- cbind(rownames(in_degree), in_degree)
rownames(in_degree) <- NULL
colnames(in_degree) <- c("Indicator","in_degree")
indonodes<-merge(x=indonodes,y=in_degree,by="Indicator",all.x=TRUE)
indonodes<-indonodes %>%
  arrange(Goal)
indonodes<-indonodes %>%
  select(Indicator, Goal, Indicator_title, in_degree)
indonodes
indonodes

Visualization

indicator_info <- read.csv("../../../Data/Text_Model_Data/indicator_att.csv")
library(stringr)
str_replace_all(indicator_info$Indicator, fixed(" "), "")

  [1] "1.1.1"   "1.2.1"   "1.2.2"   "1.3.1"   "1.4.1"   "1.4.2"   "1.5.1"   "1.5.2"   "1.5.3"   "1.5.4"   "1.a.1"   "1.a.2"  
 [13] "1.b.1"   "2.1.1"   "2.1.2"   "2.2.1"   "2.2.2"   "2.2.3"   "2.3.1"   "2.3.2"   "2.4.1"   "2.5.1"   "2.5.2"   "2.a.1"  
 [25] "2.a.2"   "2.b.1"   "2.c.1"   "3.1.1"   "3.1.2"   "3.2.1"   "3.2.2"   "3.3.1"   "3.3.2"   "3.3.3"   "3.3.4"   "3.3.5"  
 [37] "3.4.1"   "3.4.2"   "3.5.1"   "3.5.2"   "3.6.1"   "3.7.1"   "3.7.2"   "3.8.1"   "3.8.2"   "3.9.1"   "3.9.2"   "3.9.3"  
 [49] "3.a.1"   "3.b.1"   "3.b.2"   "3.b.3"   "3.c.1"   "3.d.1"   "3.d.2"   "4.1.1"   "4.1.2"   "4.2.1"   "4.2.2"   "4.3.1"  
 [61] "4.4.1"   "4.5.1"   "4.6.1"   "4.7.1"   "4.a.1"   "4.b.1"   "4.c.1"   "5.1.1"   "5.2.1"   "5.2.2"   "5.3.1"   "5.3.2"  
 [73] "5.4.1"   "5.5.1"   "5.5.2"   "5.6.1"   "5.6.2"   "5.a.1"   "5.a.2"   "5.b.1"   "5.c.1"   "6.1.1"   "6.2.1"   "6.3.1"  
 [85] "6.3.2"   "6.4.1"   "6.4.2"   "6.5.1"   "6.5.2"   "6.6.1"   "6.a.1"   "6.b.1"   "7.1.1"   "7.1.2"   "7.2.1"   "7.3.1"  
 [97] "7.a.1"   "7.b.1"   "8.1.1"   "8.2.1"   "8.3.1"   "8.4.1"   "8.4.2"   "8.5.1"   "8.5.2"   "8.6.1"   "8.7.1"   "8.8.1"  
[109] "8.8.2"   "8.9.1"   "8.10.1"  "8.10.2"  "8.a.1"   "8.b.1"   "9.1.1"   "9.1.2"   "9.2.1"   "9.2.2"   "9.3.1"   "9.3.2"  
[121] "9.4.1"   "9.5.1"   "9.5.2"   "9.a.1"   "9.b.1"   "9.c.1"   "10.1.1"  "10.2.1"  "10.3.1"  "10.4.1"  "10.4.2"  "10.5.1" 
[133] "10.6.1"  "10.7.1"  "10.7.2"  "10.7.3"  "10.7.4"  "10.a.1"  "10.b.1"  "10.c.1"  "11.1.1"  "11.2.1"  "11.3.1"  "11.3.2" 
[145] "11.4.1"  "11.5.1"  "11.5.2"  "11.6.1"  "11.6.2"  "11.7.1"  "11.7.2"  "11.a.1"  "11.b.1"  "11.b.2"  "12.1.1"  "12.2.1" 
[157] "12.2.2"  "12.3.1"  "12.4.1"  "12.4.2"  "12.5.1"  "12.6.1"  "12.7.1"  "12.8.1"  "12.a.1"  "12.b.1"  "12.c.1"  "13.1.1" 
[169] "13.1.2"  "13.1.3"  "13.2.1"  "13.2.2"  "13.3.1"  "13.a.1"  "13.b.1"  "14.1.1"  "14.2.1"  "14.3.1"  "14.4.1"  "14.5.1" 
[181] "14.6.1"  "14.7.1"  "14.a.1"  "14.b.1"  "14.c.1"  "15.1.1"  "15.1.2"  "15.2.1"  "15.3.1"  "15.4.1"  "15.4.2"  "15.5.1" 
[193] "15.6.1"  "15.7.1"  "15.8.1"  "15.9.1"  "15.a.1"  "15.b.1"  "15.c.1"  "16.1.1"  "16.1.2"  "16.1.3"  "16.1.4"  "16.2.1" 
[205] "16.2.2"  "16.2.3"  "16.3.1"  "16.3.2"  "16.3.3"  "16.4.1"  "16.4.2"  "16.5.1"  "16.5.2"  "16.6.1"  "16.6.2"  "16.7.1" 
[217] "16.7.2"  "16.8.1"  "16.9.1"  "16.10.1" "16.10.2" "16.a.1"  "16.b.1"  "17.1.1"  "17.1.2"  "17.2.1"  "17.3.1"  "17.3.2" 
[229] "17.4.1"  "17.5.1"  "17.6.1"  "17.7.1"  "17.8.1"  "17.9.1"  "17.10.1" "17.11.1" "17.12.1" "17.13.1" "17.14.1" "17.15.1"
[241] "17.16.1" "17.17.1" "17.18.2" "17.18.3" "17.19.1" "17.19.2"

Textdata <- datatable(indicator_info, rownames=TRUE, caption=htmltools::tags$caption(style="caption-side: bottom; text-align: center;", "Innovative counties in the U.S."), filter="top", extensions="Buttons", options=list(dom = "Bfrtip", buttons = c("colvis", "copy", "csv", "excel", "pdf", "print")))
Textdata

Guatemala (Not finished)

Data preparation

edgelistguate <- read.csv("~/Documents/GitHub/G5055_Practicum_Project2/Data/PCA_results/gua_coefficients_sig.csv")
#Some preprocessing
edgelistguate<-edgelistguate%>%
  select(Var1, Var2, value)%>%
  filter(Var1!=Var2)
names(edgelistindo)<-c("from","to","value")
edgelistguate

Visualization

guatenodes <- edgelistguate %>%
  select(Var1, Var2)
guatenodes <- data.frame(indicatorname = unlist(guatenodes, use.names = FALSE))
guatenodes <- distinct(guatenodes)
#guatenodes$goal <- stri_match_first_regex(guatenodes$indicator, "(.*?)\\.")[,2]
#guatenodes$goal <-as.numeric(guatenodes$goal)
g3<-graph_from_data_frame(edgelistguate, directed=FALSE, vertices=guatenodes)
guatenodes